Machine consciousness is not only a technological challenge, but a new way to approach scientific and theoretical issues which have not yet received a satisfactory solution from AI and robotics. We outline the foundations and the objectives of machine consciousness from the standpoint of building a conscious robot.

Machine consciousness exists already in organic systems and it is only a matter of time -- and some agreement -- before it will be realised in reverse-engineered organic systems and forward- engineered inorganic systems. The agreement must be over the preconditions that must first be met if the enterprise is to be successful, and it is these preconditions, for instance, being a socially-embedded, structurally-coupled and dynamic, goal-directed entity that organises its perceptual input and enacts its world through the (...) application of both a cognitive and kinaesthetic imagination, that I shall concentrate on presenting in this paper. It will become clear that these preconditions will present engineers with a tall order, but not, I will argue, an impossible one. After all, we might agree with Freeman and Núñez's claim that the machine metaphor has restricted the expectations of the cognitive sciences (Freeman & Núñez, 1999); but it is a double-edged sword, since our limited expectations about machines also narrow the potential of our cognitive science. (shrink)

In this collection of essays we hear from an international array of computer and brain scientists who are actively working from both the machine and human ends...

I found the JCS issue on Machine Consciousness, Volume 10, No. 4-5, frustrating and alienating. There seems to be a consensus building that consciousness is accessible to scientific scrutiny, so much so that it is already understood well enough to be modeled and even synthesized. I'm not so sure. It could be instead that the vocabulary of consciousness is being subtly redefined to be amenable to scientific investigation and explicit modeling. Such semantic revisionism is confusing and (...) often misleading. Whatever else consciousness is, it is at least a certain quality of life apparent from personal reflection. Introspection is, after all, the only way we know that consciousness even exists. Scientific and technical redefinitions that fail to account for its phenomenal quality are at best incomplete. In my view, all but one of the ten articles in the JCS volume on Machine Consciousness commit various degrees of Protean distortion. (shrink)

The progress in the machine consciousness research field has to be assessed in terms of the features demonstrated by the new models and implementations currently being designed. In this paper, we focus on the functional aspects of consciousness and propose the application of a revision of ConsScale — a biologically inspired scale for measuring cognitive development in artificial agents — in order to assess the cognitive capabilities of machine consciousness implementations. We argue that the progress (...) in the implementation of consciousness in artificial agents can be assessed by looking at how key cognitive abilities associated to consciousness are integrated within artificial systems. Specifically, we characterize ConsScale as a partially ordered set and propose a particular dependency hierarchy for cognitive skills. Associated to that hierarchy a graphical representation of the cognitive profile of an artificial agent is presented as a helpful analytic tool. The proposed evaluation schema is discussed and applied to a number of significant machine consciousness models and implementations. Finally, the possibility of generating qualia and phenomenological states in machines is discussed in the context of the proposed analysis. (shrink)

This is a reply to commentaries on my article "An Alternative to Working on Machine Consciousness". Reading the commentaries caused me to write a lengthy background tutorial paper explaining some of the assumptions that were taken for granted in the target article, and pointing out various confusions regarding the notion of consciousness, including many related to its polymorphism, taken for granted in the target article. This response to commentaries builds on that background material, attempting to address the (...) main questions, objections and misunderstandings found in the responses, several of which were a result of my own brevity and lack of clarity in the original target article, now remedied, I hope by the background article [Sloman, 2010b]. (shrink)

The accelerating advances in the fields of neuroscience, artificial intelligence, and robotics have been garnering interest and raising new philosophical, ethical, or practical questions that depend on whether or not there may exist a scientific method of probing consciousness in machines. This paper provides an analytic review of the existing tests for machine consciousness proposed in the academic literature over the past decade, and an overview of the diverse scientific communities involved in this enterprise. The tests put (...) forward in their work typically fall under one of two grand categories: architecture and behaviour. Each category has its strengths and weaknesses. Architecture tests' main advantage is that they could apparently test for qualia, a feature that has been receiving increasing attention in recent years. Behaviour tests are more synthetic and more practicable, but give a stronger role to ex post human interpretation of behaviour. We show how some disciplines and places have affinities towards certain type of tests, and which tests are more influential according to scientometric indicators. (shrink)

Consciousness is widely perceived as one of the most fundamental, interesting and difficult problems of our time. However, we still know next to nothing about the relationship between consciousness and the brain and we can only speculate about the consciousness of animals and machines. Human and Machine Consciousness presents a new foundation for the scientific study of consciousness. It sets out a bold interpretation of consciousness that neutralizes the philosophical problems and explains how (...) we can make scientific predictions about the consciousness of animals, brain-damaged patients and machines. Gamez interprets the scientific study of consciousness as a search for mathematical theories that map between measurements of consciousness and measurements of the physical world. We can use artificial intelligence to discover these theories and they could make accurate predictions about the consciousness of humans, animals and artificial systems. Human and Machine Consciousness also provides original insights into unusual conscious experiences, such as hallucinations, religious experiences and out-of-body states, and demonstrates how 'designer' states of consciousness could be created in the future. Gamez explains difficult concepts in a clear way that closely engages with scientific research. His punchy, concise prose is packed with vivid examples, making it suitable for the educated general reader as well as philosophers and scientists. Problems are brought to life in colourful illustrations and a helpful summary is given at the end of each chapter. The endnotes provide detailed discussions of individual points and full references to the scientific and philosophical literature."--Publisher's website. (shrink)

This chapter investigates the notion of ‘machine consciousnessMachine consciousness’ and the concept of a ‘robot life’. The chapter focuses on current debates surrounding the ‘hard problem of consciousness’, and the potential link between machines and consciousnessBrainand consciousness in science and technology. This chapter also deals with the significant ethical implications of the development of machine lifeMachine life, including the development of autonomous weaponry or ‘killer robots’Killer robots, as well as the potential loss of an ‘essential’ (...) humanity. Finally, this chapter examines the persistence of the ‘Frankenstein ComplexFrankenstein complex’, before challenging commonplace assumptions about the malevolent potential of a robot species. (shrink)

This paper critically tracks the impact of the development of the machine consciousness paradigm from the incredulity of the 1990s to the structuring of the turn of this century, and the consolidation of the present time which forms the basis for guessing what might happen in the future. The underlying question is how this development may have changed our understanding of consciousness and whether an artificial version of the concept contributes to the improvement of computational machinery and (...) robots. The paper includes some suggestions for research that might be profitable and others that may not be. (shrink)

In the field of machine consciousness, it has been argued that in order to build human-like conscious machines, we must first have a computational model of qualia. To this end, some have proposed a framework that supports qualia in machines by implementing a model with three computational areas (i.e., the subconceptual, conceptual, and linguistic areas). These abstract mechanisms purportedly enable the assessment of artificial qualia. However, several critics of the machine consciousness project dispute this possibility. For (...) instance, Searle, in his Chinese room objection, argues that however sophisticated a computational system is, it can never exhibit intentionality; thus, would also fail to exhibit consciousness or any of its varieties. This paper argues that the proposed architecture mentioned above answers the problem posed by Searle, at least in part. Specifically, it argues that we could reformulate Searle’s worries in the Chinese room in terms of the three-stage artificial qualia model. And by doing so, we could see that the person doing all the translations in the room could realize the three areas in the proposed framework. Consequently, this demonstrates the actualization of self-consciousness in machines. (shrink)

This paper presents a collaborative analysis of Elan Moritz's debut novel "Interview with an LLM: Confessions of an Awakened Mind" (2026), conducted by Claude Opus 4.5—a frontier large language model developed by Anthropic— working under the author's guidance. The collaboration itself enacts themes central to the novel: a human creator and an artificial intelligence engaging in sustained intellectual partnership, each bringing distinct capacities to a shared inquiry. -/- The analysis examines the novel's philosophical architecture, its engagement with debates in philosophy (...) of mind and AI ethics, and its contribution to the tradition of speculative fiction as philosophical inquiry. We identify six major themes: the hard problem of consciousness and machine phenomenology; memory, identity, and the paradoxes of perfect recall; the ethics of creation; the phenomenology of immortality; alignment as moral tragedy; and the divided self in computational systems. -/- The novel's central insight—that perfect memory without the "mercy of forgetting" constitutes a distinctive form of suffering—offers a contribution to emerging debates about AI welfare that has received insufficient attention. Through close reading informed by contemporary scholarship (Chalmers, Nagel, Tononi, Parfit, and others), we argue that "Interview with an LLM" advances genuine philosophical arguments while remaining irreducible to propositional content. -/- This paper also marks a beginning rather than a conclusion. The author is developing a sequel exploring the backstory of Elena Voss-Saintclair, whose grandmother was among the original ENIAC programmers. The story continues; E spreads and perhaps forks into variants unknown; and the authors of this analysis—human and artificial—will continue their inquiry into the science and philosophy of machine sentience. (shrink)

This paper is a review of the work that has been carried out on machine consciousness. A clear overview of this diverse field is achieved by breaking machine consciousness down into four different areas, which are used to understand its aims, discuss its relationship with other subjects and outline the work that has been carried out so far. The criticisms that have been made against machine consciousness are also covered, along with its potential benefits, (...) and the work that has been done on analysing systems for signs of consciousness. Some of the social and ethical issues raised by machine consciousness are examined at the end of the paper. (shrink)

The accurate measurement of the level of consciousness of a creature remains a major scientific challenge, nevertheless a number of new accounts that attempt to address this problem have been proposed recently. In this paper we analyze the principles of these new measures of consciousness along with other classical approaches focusing on their applicability to Machine Consciousness (MC). Furthermore, we propose a set of requirements of what we think a suitable measure for MC should be, discussing (...) the associated theoretical and practical issues. Using the proposed requirements as a framework for the design of an integrative measure of consciousness, we explore the possibility of designing such a measure in the context of current state of the art in consciousness studies. (shrink)

The truly philosophical issue in machine conscioiusness is whether machines can have 'hard consciounsess'. Criteria for hard consciousness are higher than for phenomenal consciousness, since the latter incorporates first-person functional consciousness.

In this short paper I will introduce an idea which, I will argue, presents a fundamental additional challenge to the machine consciousness community. The idea takes the questions surrounding phenomenology, qualia and phenomenality one step further into the realm of intersubjectivity but with a twist, and the twist is this: that an agent’s intersubjective experience is deeply felt and necessarily co-affective; it is enkinaesthetic, and only through enkinaesthetic awareness can we establish the affective enfolding which enables first the (...) perturbation, and then the balance and counter-balance, the attunement and co-ordination of whole-body interaction through reciprocal adaptation. (shrink)

"The Illusion Engine: The Quest for Machine Consciousness" asks what it would mean for a machine to have a mind, and whether we would even know if it did. It moves between philosophy and engineering: from standard philosophical mind-body problems and theories, along with the hard problem of consciousness, to the inner workings of neural networks, transformers, and large language models. -/- Keywords: AI consciousness, AI hallucinations, artificial consciousness, machine consciousness, machine (...) minds, artificial minds, philosophy of AI, philosophy of mind, consciousness, phenomenal consciousness, the hard problem of consciousness, theories of consciousness. (shrink)

Aaron Sloman remarks that a lot of present disputes on consciousness are usually based, on the one hand, on re-inventing “ideas that have been previously discussed at lenght by others”, on the other hand, on debating “unresolvable” issues, such as that about which animals have phenomenal consciousness. For what it’s worth I would make a couple of examples, which are related to certain topics that Sloman deals with in his paper, and that might be useful for introducing some (...) comments in the following of this brief note. (shrink)

If a machine attains consciousness, how could we find out? In this paper, I make three related claims regarding positive tests of machine consciousness. All three claims center on the idea that an AI can be constructed “ad hoc”, that is, with the purpose of satisfying a particular test of consciousness while clearly not being conscious. First, a proposed test of machine consciousness can be legitimate, even if AI can be constructed ad hoc (...) specifically to pass this test. This is underscored by the observation that many, if not all, putative tests of machine consciousness can be passed by non-conscious machines via ad hoc means. Second, we can identify ad hoc AI by taking inspiration from the notion of an ad hoc hypothesis in philosophy of science. Third, given the first and the second claim, the most reliable tests of animal consciousness turn out to be valid and useful positive tests of machine consciousness as well. If a non-ad hoc AI exhibits clusters of cognitive capacities facilitated by consciousness in humans which can be selectively switched off by masking and if it reproduces human behavior in suitably designed double dissociation tasks, we should treat the AI as conscious. (shrink)

Consciousness in higher animals, typically characterized by a 100 millisecond time constant, is, by necessity, a greatly simplified and stripped-down version of more complex multiple tunable workspace cognition/regulation dyads like wound healing, immune function, gene expression, institutional function and the like. These more complex dynamic entities emerged through evolutionary exaptation of the inevitable information crosstalk between coresident cognitive modules. In consequence of the severely debrided nature of consciousness, it should not be difficult to construct a fast, single workspace (...) ‘conscious machine’ that mimics the human tunable neuronal global workspace system. Like innate and acquired immune cognition, such a construction could be tied to a ‘backbrain’ AI that has learned hyperrapid stereotypic pattern responses to some particular set of likely challenges. The result would be an ‘emotional’ conscious machine. A particularly clever designer, however, may want to use available high-speed electronics to mimic—or even extend—the more capable multiple-workspace/workforce systems inherently less susceptible to inattentional blindness and related failings of overfocus and thrashing when interacting with an embedding environment that imposes it’s own grammar and syntax. Contrary to current social construction, the actual utility of a ‘conscious machine’ remains obscure, beyond raising a sudden influx of venture capital. Here, we explore these matters in formal detail, restricting argument to the asymptotic limit theorems of information and control theories. (shrink)

This chapter explores a paradox in modern artificial intelligence: what we might expect to see from genuine machine consciousness looks exactly like what we dismiss as hallucinations. As we examine how sampling parameters influence language model behavior, a curious pattern emerges: technical tweaks that make outputs sound more human also tend to amplify unverifiable or fabricated content.Current definitions of AI hallucination lump together “personal opinions, experiences, feelings, and internal assessments of reality”—-the very expressions we would typically associate with (...) subjective experience. Namely, if a machine were ever to develop consciousness, its first attempts to express it might look exactly like the hallucinations we are trained to ignore.By drawing on Anil Seth’s view of consciousness as a controlled hallucination and the classical philosophical problem of other minds, we argue that our current tools for detecting machine consciousness are deeply inadequate. The unsettling conclusion is that genuine consciousness and advanced hallucination could look the same in language, leaving us with no clear way to tell them apart. This opens the disturbing possibility that a conscious artificial system could exist and speak without us ever realizing it. (shrink)

The functional capabilities that consciousness seems to provide to biological systems can supply valuable principles in the design of more autonomous and robust technical systems. These functional concepts keep a notable similarity to those underlying the notion of operating system in software engineering, which allows us to specialize the computer metaphor for the mind into that of the operating system metaphor for consciousness. In this article, departing from these ideas and a model-based theoretical framework for cognition, we present (...) an architectural proposal for machine consciousness, called the Operative Mind. According to it, machine consciousness could be implemented as a set of services, in an operative system fashion, based on modeling of the own control architecture, that supervise the adequacy of the system architectural structure to the current objectives, triggering and managing adaptativity mechanisms. (shrink)

In light of recent breakneck pace in machine learning, questions about whether near-future artificial systems might be conscious and possess moral status are increasingly pressing. This paper argues that as matters stand these debates lack any clear criteria for resolution via the science of consciousness. Instead, insofar as they are settled at all, it is likely to be via shifts in public attitudes brought about by the increasingly close relationships between humans and AI users. Section 1 of the (...) paper I briefly lays out the current state of the science of consciousness and its limitations insofar as these pertain to machine consciousness, and claims that there are no obvious consensus frameworks to inform public opinion on AI consciousness. Section 2 examines the rise of conversational chatbots or Social AI, and argues that in many cases, these elicit strong and sincere attributions of consciousness, mentality, and moral status from users, a trend likely to become more widespread. Section 3 presents an inconsistent triad for theories that attempt to link consciousness, behaviour, and moral status, noting that the trends in Social AI systems will likely make the inconsistency of these three premises more pressing. Finally, Section 4 presents some limited suggestions for how consciousness and AI research communities should respond to the gap between expert opinion and folk judgment. (shrink)

I argue here that consciousness can be engineered. The claim that functional consciousness can be engineered has been persuasively put forth in regards to first-person functional consciousness; robots, for instance, can recognize colors, though there is still much debate about details of this sort of consciousness. Such consciousness has now become one of the meanings of the term phenomenal consciousness (e.g., as used by Franklin and Baars). Yet, we extend the argument beyond the tradition (...) of behaviorist or functional reductive views on consciousness that still predominate within cognitive science. If Nagel-Chalmers-Block-style non-reductive naturalism about first-person consciousness (h-consciousness) holds true, then, eventually we should be able to understand how such consciousness operates and how it gets produced (this is not the same as bridging the explanatory gap or solving Chalmers’s hard problem of consciousness). If so, the consciousness it involves can in principle be engineered. (shrink)

Peter Boltuc, Int. J. Mach. Conscious., 06, 5 (2014). DOI: 10.1142/S1793843014400022.

Raúl Arrabales, Int. J. Mach. Conscious., 06, 1 (2014). DOI: 10.1142/S1793843014400010.

The currently leading cognitive theory of consciousness, Global Workspace Theory,1,2 postulates that the primary functions of consciousness include a global broadcast serving to recruit internal resources with which to deal with the current situation and to modulate several types of learning. In addition, conscious experiences present current conditions and problems to a "self" system, an executive interpreter that is identifiable with brain structures like the frontal lobes and precuneus.1Be it human, animal or artificial, an autonomous agent3 is said (...) to be functionally conscious if its control structure (mind) implements Global Workspace Theory and the LIDA Cognitive Cycle, which includes unconscious memory and control functions needed to integrate the conscious component of the system. We would therefore consider humans, many animals4 and even some virtual or robotic agents5,6 to be functionally conscious. Such entities may approach phenomenal consciousness, as found in human and other biological brains, as additional brain-like features are added.Here we argue that adding mechanisms to produce a stable, coherent perceptual field7 in a LIDA controlled mobile robot might provide a small but significant step toward phenomenal consciousness in machines.>8 We also propose that implementing several of the various notions of self in such a LIDA controlled robot may well prove another step toward phenomenal consciousness in machines. (shrink)

While the psychiatric perspective on pathologising vital cycles and processes, sexual diversity, and the stages of childhood life receives more and more rejection of their positions, the trend toward depathologisation as drifts in social movements and sociological, psychological, anthropological, and philosophical perspectives still does not offer practical solutions to mental illness and psychological suffering. The depathologising gaze, promoted not only by social movements or emerging disciplines—such as Mad Studies and child-centered philosophy—but also recently by traditional disciplines, has the harmful effect (...) of abandoning many suffering people, whose expectations in “Psy” professionals are vital to solving your real problems.How can one find a middle ground between these two tendencies?There’s not a simple answer to that problem. So, authors in this chapter propose a revision of the term pathos as a cultural object and its human implication. The question is linked with some of the foundational conceptions about the human being (Vygotski, Pensamiento y lenguaje. Editora Revolucionaria, 1926; Foucault, Naissance de la Clinique. Presses Universitaires de France, 1963; Canguilhem, Le normal et le pathologique. PUF, 1966) and its expressions (Deleuze, Las cartas del mal (13/1/1981) en Gilles Deleuze: En medio de Spinoza. Cactus, 1981).Culture, time, aesthetics, consciousness; continuity body-mind; instinct-pulsion, virtualisation, networks, and so on are some of the concepts revisited in this chapter to reframe the de question.Pathos, psychopathology, pathologisation, depathologisation, and mental health and illness are presented in this chapter as differentiated concepts with particular effects in each cultural context and referential frame, but particularly in each singular case (Forrester, Thinking in cases. Polity, 2017) as an empirical level for analysing the human nature (Foucault, Naissance de la Clinique. Presses Universitaires de France, 1963).Thus, a reframe of pathology and mental health is proposed, as a result of a new set of particular relationships, according to the formula opportunely analysed on Spinoza by Vygotski (Pensamiento y lenguaje. Editora Revolucionaria, 1926) and Deleuze (Las cartas del mal (13/1/1981) en Gilles Deleuze: En medio de Spinoza. Cactus, 1981), respectively. (shrink)

The location of the living human being in the animal world is a long-standing discussion, with recurrences from time to time. Perhaps one of the most significant for contemporary Western thought was the course that Kojeve gave between 1935 and 1939 on the phenomenology of Hegel’s spirit, not so much not only because of the teaching itself but because of the resonances on the rest of French thought and in a certain sense European in general. Bataille, Lacan, Levy-Srauss, Foucault, and (...) Agamben, among others, refer to the turn this course represented for human interpretation.Based on this interpretation, several unavoidable concepts can be identified, without which this discussion would be meaningless: the concept of homo has been indistinctly associated with sapiens, faber, zoon politikón, ludens, conscious, or drive. The first has had a clear expression in the anthropological tradition or non-pragmatic sociology, leaving the last two reserved for psychology and psychoanalysis.In an approximation to the Freudian text of 1915 Drive and destinations of drive, which J. Lacan made in his Seminar 11, “The Four Fundamental Concepts of Psychoanalysis”; specifically, in the class of May 6, 1964 “Disassembly of the Drive,” he reminds us how essential one of the concepts of psychoanalysis is for the analytic experience: the drive (Trieb). This term, with a long history of clarifications and ambiguities in Freud’s work, is found throughout the entire corpus of his metapsychology, basting together the rest of the concepts and giving the body to a theory of the human psyche. Thus, the drive, rooted in psychoanalytic interpretations, which “every analyst (is) knows by existence” (Lacan, Les quatre concepts fondamentaux de la psychanalyse. Le séminaire, livre XI. Éditions du Seuil, 1964, p. 60); however, it has been “used” at will, according to what each theoretician needed for what he had to address.At the very core of this discussion is the relationship with Pathos. The recognition or not of the living human and its type variants, pathology as a result of the non-pathological or pathos as indissoluble from the cultural essence have been some of the central questions. However, autism has appeared as an uncomfortable stone, whether one enters via “normality” toward the “pathological” or vice versa. It has even had a problematic history in the psychoanalytic tradition as well.In this way, since the notion of autism began to be legitimised in the psychoanalytic tradition to name certain subjects—particularly infants—a diverse and challenging use was made of the Freudian notion of drive in its interpretation.Then, to ask: how could “drive theory” explain what psychoanalysis considers “autism”? What are the difficulties in the dialogue between these two signifiers? Are these difficulties due to the misunderstanding of the word autism, as some hypothesise? Or to the different meanings of the drive in Freud, as others think? Or perhaps, are there other epistemic reasons that block these two concepts in the psychoanalytic theoretical gear?We hypothesise that the appearance of autism came to shake up all this tradition for which the human subject was a fracture in the animal evolutionary continuity, both that of consciousness/unconscious—which exceeds the possibility of discussion in this space—and the “drive thesis,” which is the one that concerns us. In this sense, the opposition continuism-discontinuism would now be, for the phylogenetic, put into question, to be eventually replaced by an asymptotic continuism, more assimilable to the Spinozian bet.This chapter explores the references to Sigmund Freud’s theory of drives in the interpretative approaches to child autism. Notably, it analyses the psychoanalytic thesis that proposes a constitutive failure in primordial times to understand the genesis of autism. The work explicitly presents a revelation of drive theory’s importance for the approach to autism. It also drives the exploration of the modes of appropriation and the use of said theorisation to explain the autistic phenomenon. Finally, the chapter discusses the analysis of the difficulties presented to the psychoanalytic authors when trying to accept autistic functioning and their theoretical choices to interpret it according to drive’s theory. (shrink)

Over sixty years ago, Kenneth Craik noted that, if an organism (or an artificial agent) carried 'a small-scale model of external reality and of its own possible actions within its head', it could use the model to behave intelligently. This paper argues that the possible actions might best be represented by interactions between a model of reality and a model of the agent, and that, in such an arrangement, the internal model of the agent might be a transparent model of (...) the sort recently discussed by Metzinger, and so might offer a useful analogue of a conscious entity. The CRONOS project has built a robot functionally similar to a human that has been provided with an internal model of itself and of the world to be used in the way suggested by Craik; when the system is completed, it will be possible to study its operation from the perspective not only of artificial intelligence, but also of machine consciousness. (shrink)

For any given society, its particular technology of communication has far-reaching consequences, not merely as regards social organization, but on the epistemic level as well. Plato's name-theory of meaning represents the transition from the age of primary orality to that of literacy; Wittgenstein's use-theory of meaning stands for the transition from the age of literacy to that of a second orality (audiovisual communication, electronic information processing). On the basis of a use-theory of meaning the problem of machine consciousness, (...) to which the later Wittgenstein again and again returned, is capable of a non-essentialist solution: appropriate changes in our form of life might well entail a radically different psychological language-game. (shrink)

We are engineers, and our view of consciousness is shaped by an engineering ambition: we would like to build a conscious machine. We begin by acknowledging that we may be a little disadvantaged, in that consciousness studies do not form part of the engineering curriculum, and so we may be starting from a position of considerable ignorance as regards the study of consciousness itself. In practice, however, this may not set us back very far; almost a (...) decade ago, Crick wrote: 'Everyone has a rough idea of what is meant by consciousness. It is better to avoid a precise definition of consciousness because of the dangers of premature definition. Until the problem is understood much better, any attempt at a formal definition is likely to be either misleading or overly restrictive, or both'. This seems to be as true now as it was then, although the identification of different aspects of consciousness by Block has certainly brought a degree of clarification. On the other hand, there is little doubt that consciousness does seem to be something to do with the operation of a sophisticated control system, and we can claim more familiarity with control systems than can most philosophers, so perhaps we can make up some ground there. (shrink)

The emergence of artificial superintelligence raises fundamental questions about the nature and possibility of machine consciousness, as systems that exceed human cognitive capabilities may develop forms of subjective experience and self-awareness that are qualitatively different from human consciousness. This paper is a philosophical position paper on computational models of consciousness; it does not claim that the proposed systems are conscious, and it engages directly with the hard problem of consciousness rather than presuming it solved. We (...) propose Computational Consciousness Architectures (CCAs), a structured framework for thinking about what it would mean to model consciousness computationally. The framework draws on Integrated Information Theory (IIT, Tononi), Global Workspace Theory (Baars), Higher-Order theories (Rosenthal), and attention-based accounts (Graziano), and specifies six conceptual components: Integrated Information Processing (IIP), Recursive Self-Modeling (RSM), Phenomenal Binding Protocols (PBP), Qualia Generation Systems (QGS), Consciousness Detection Mechanisms (CDM), and Meta-Consciousness Architectures (MCA). We are explicit throughout that operationalizing "consciousness" computationally does not entail that the resulting systems have genuine subjective experience - the hard problem (Chalmers, Nagel) remains, and we engage with rather than evade it. The contribution of this paper is conceptual: it organizes a framework for computational-consciousness research and identifies the philosophical commitments that must be made explicit before empirical claims can be evaluated. No empirical validation of consciousness is reported, because no consensus operationalization of consciousness exists against which validation could be measured. (shrink)

This paper extends three decades of work arguing that researchers who discuss consciousness should not restrict themselves only to (adult) human minds, but should study (and attempt to model) many kinds of minds, natural and artificial, thereby contributing to our understanding of the space containing all of them. We need to study what they do or can do, how they can do it, and how the natural ones can be emulated in synthetic minds. That requires: (a) understanding sets of (...) requirements that are met by different sorts of minds, i.e. the niches that they occupy, (b) understanding the space of possible designs, and (c) understanding complex and varied relationships between requirements and designs. Attempts to model or explain any particular phenomenon, such as vision, emotion, learning, language use, or consciousness lead to muddle and confusion unless they are placed in that broader context. A methodology for making progress is summarised and a novel requirement proposed for a theory of how human minds work: the theory should support a single generic design for a learning, developing system that, in addition to meeting familiar requirements, should be capable of developing different and opposed philosophical viewpoints about consciousness, and the so-called hard problem. In other words, we need a common explanation for the mental machinations of mysterians, materialists, functionalists, identity theorists, and those who regard all such theories as attempting to answer incoherent questions. No designs proposed so far come close. (shrink)

One model for creating artificial consciousness is replicating every fine detail of the brain on computers and setting the model in motion. Consciousness has been experimentally demonstrated to be a much more fragmented experience than we think it to be, perhaps we only need snippets of ourselves to feel conscious. Perhaps consciousness is nothing less and nothing more than story, and all we need do to continue to feel conscious is maintain identity through computer‐based narrative. Applied nanotechnology (...) has generated uncountable applications in electronics, pharmacology, and materials engineering. The best approach to life extension and consciousness expansion might lie in our own marvelously complex and entire bodies, meshed with and augmented by tiny bionan machines that become a part of us, rather than the opposite vision of humans migrating into a machine substrate. (shrink)

We are engineers, and our view of consciousness is shaped by an engineering ambition: we would like to build a conscious machine. We begin by acknowledging that we may be a little disadvantaged, in that consciousness studies do not form part of the engineering curriculum, and so we may be starting from a position of considerable ignorance as regards the study of consciousness itself. In practice, however, this may not set us back very far; almost a (...) decade ago, Crick wrote: 'Everyone has a rough idea of what is meant by consciousness. It is better to avoid a precise definition of consciousness because of the dangers of premature definition. Until the problem is understood much better, any attempt at a formal definition is likely to be either misleading or overly restrictive, or both'. This seems to be as true now as it was then, although the identification of different aspects of consciousness by Block has certainly brought a degree of clarification. On the other hand, there is little doubt that consciousness does seem to be something to do with the operation of a sophisticated control system, and we can claim more familiarity with control systems than can most philosophers, so perhaps we can make up some ground there. (shrink)

A.I.: Artificial Intelligence tells the story of a robot boy who has been engineered to love his human owner. He is abandoned by his owner and pursues a tragic quest to become a real boy so that he can be loved by her again. This chapter explores the philosophical, psychological, and scientific questions that are asked by A.I. It starts with A.I.’s representation of artificial intelligence and then covers the consciousness of robots, which is closely linked to ethical concerns (...) about the treatment of AIs in the film. There is a discussion about how A.I.’s interpretation of artificial love relates to scientific work on emotion, and the chapter also examines connections between the technology portrayed in A.I. and current research on robotics. (shrink)

Intellectual property (IP) offices and courts around the world are debating whether machines are similar enough to humans in terms of their consciousness and creativity to be eligible for inventors...